no code implementations • 27 Oct 2024 • Dragos Gorduza, Yaxuan Kong, Xiaowen Dong, Stefan Zohren

We investigate the effectiveness of a momentum trading signal based on the coverage network of financial analysts.

1 code implementation • 18 Oct 2024 • Shuo Tang, Xianghe Pang, Zexi Liu, Bohan Tang, Rui Ye, Xiaowen Dong, Yanfeng Wang, Siheng Chen

Post-training is essential for enabling large language models (LLMs) to follow human instructions.

no code implementations • 14 Oct 2024 • Mathieu Alain, So Takao, Xiaowen Dong, Bastian Rieck, Emmanuel Noutahi

The problem of classifying graphs is ubiquitous in machine learning.

no code implementations • 25 Aug 2024 • Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong, Michael Bronstein

NSTs are implemented as three neural networks trained in an end-to-end manner: an embedding network, which learns to optimize the location of nodes as events in the spacetime manifold, and two other networks that optimize the space and time geometries in parallel, which we call a neural (quasi-)metric and a neural partial order, respectively.

no code implementations • 24 Jun 2024 • Baskaran Sripathmanathan, Xiaowen Dong, Michael Bronstein

We further show that at sufficiently low SNRs, for LS reconstruction we have a $\Lambda$-shaped error curve and for GLR reconstruction, a sample size of $ \mathcal{O}(\sqrt{N})$, where $N$ is the total number of vertices, results in lower reconstruction error than near full observation.

no code implementations • 15 Jun 2024 • Yuqi Nie, Yaxuan Kong, Xiaowen Dong, John M. Mulvey, H. Vincent Poor, Qingsong Wen, Stefan Zohren

We then highlight this survey for categorizing the existing literature into key application areas, including linguistic tasks, sentiment analysis, financial time series, financial reasoning, agent-based modeling, and other applications.

no code implementations • 13 Jun 2024 • Marco Pacini, Xiaowen Dong, Bruno Lepri, Gabriele Santin

In this paper, we propose a theoretical framework to investigate the separation power of equivariant neural networks with point-wise activations.

no code implementations • 31 May 2024 • Fernando Moreno-Pino, Álvaro Arroyo, Harrison Waldon, Xiaowen Dong, Álvaro Cartea

To address this challenge, we introduce the Rough Transformer, a variation of the Transformer model that operates on continuous-time representations of input sequences and incurs significantly lower computational costs.

no code implementations • 24 May 2024 • Jacob Bamberger, Federico Barbero, Xiaowen Dong, Michael Bronstein

The dominant paradigm for learning on graph-structured data is message passing.

1 code implementation • 24 May 2024 • Huidong Liang, Xingchen Wan, Xiaowen Dong

We address the problem of optimizing over functions defined on node subsets in a graph.

1 code implementation • 28 Mar 2024 • Mihai Cucuringu, Xiaowen Dong, Ning Zhang

This paper studies the directed graph clustering problem through the lens of statistics, where we formulate clustering as estimating underlying communities in the directed stochastic block model (DSBM).

1 code implementation • 23 Mar 2024 • Isabelle Lorge, Li Zhang, Xiaowen Dong, Janet B. Pierrehumbert

The rise of social media platforms has led to an increase in polarised online discussions, especially on political and socio-cultural topics such as elections and climate change.

no code implementations • 15 Mar 2024 • Fernando Moreno-Pino, Álvaro Arroyo, Harrison Waldon, Xiaowen Dong, Álvaro Cartea

To mitigate this, we introduce the Rough Transformer, a variation of the Transformer model which operates on continuous-time representations of input sequences and incurs significantly reduced computational costs, critical for addressing long-range dependencies common in medical contexts.

no code implementations • 11 Mar 2024 • Shuo Tang, Rui Ye, Chenxin Xu, Xiaowen Dong, Siheng Chen, Yanfeng Wang

In this paper, we propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs.

no code implementations • 8 Feb 2024 • Bohan Tang, Zexi Liu, Keyue Jiang, Siheng Chen, Xiaowen Dong

Hypergraphs are crucial for modelling higher-order interactions in real-world data.

no code implementations • 17 Jan 2024 • Marco Pacini, Xiaowen Dong, Bruno Lepri, Gabriele Santin

Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains.

1 code implementation • 18 Dec 2023 • Zexi Liu, Bohan Tang, Ziyuan Ye, Xiaowen Dong, Siheng Chen, Yanfeng Wang

Hypergraphs play a pivotal role in the modelling of data featuring higher-order relations involving more than two entities.

1 code implementation • 15 Dec 2023 • Bohan Tang, Siheng Chen, Xiaowen Dong

Hypergraphs are vital in modelling data with higher-order relations containing more than two entities, gaining prominence in machine learning and signal processing.

no code implementations • 9 Sep 2023 • Haitz Saez de Ocariz Borde, Alvaro Arroyo, Ismael Morales, Ingmar Posner, Xiaowen Dong

Recent studies propose enhancing machine learning models by aligning the geometric characteristics of the latent space with the underlying data structure.

no code implementations • 27 Aug 2023 • Bohan Tang, Siheng Chen, Xiaowen Dong

However, existing methods either adopt simple pre-defined rules that fail to precisely capture the distribution of the potential hypergraph structure, or learn a mapping between hypergraph structures and node features but require a large amount of labelled data, i. e., pre-existing hypergraph structures, for training.

no code implementations • 23 Aug 2023 • Xingyue, Pu, Stefan Zohren, Stephen Roberts, Xiaowen Dong

Network momentum provides a novel type of risk premium, which exploits the interconnections among assets in a financial network to predict future returns.

no code implementations • 22 Aug 2023 • Xingyue, Pu, Stephen Roberts, Xiaowen Dong, Stefan Zohren

We investigate the concept of network momentum, a novel trading signal derived from momentum spillover across assets.

no code implementations • 18 Aug 2023 • Valentina Semenova, Dragos Gorduza, William Wildi, Xiaowen Dong, Stefan Zohren

Our initial experiments decompose the forum using a large language topic model and network tools.

no code implementations • 1 Aug 2023 • Chao Zhang, Xingyue Pu, Mihai Cucuringu, Xiaowen Dong

We present a novel methodology for modeling and forecasting multivariate realized volatilities using customized graph neural networks to incorporate spillover effects across stocks.

no code implementations • 1 Jul 2023 • Baskaran Sripathmanathan, Xiaowen Dong, Michael Bronstein

We show that under the setting of noisy observation and least-squares reconstruction this is not always the case, characterising the behaviour both theoretically and experimentally.

1 code implementation • 20 Jun 2023 • Pierre Osselin, Henry Kenlay, Xiaowen Dong

Certifying the robustness of a graph-based machine learning model poses a critical challenge for safety.

no code implementations • 6 Jun 2023 • Felix L. Opolka, Yin-Cong Zhi, Pietro Liò, Xiaowen Dong

Graph classification aims to categorise graphs based on their structure and node attributes.

1 code implementation • 13 May 2023 • Benjamin Gutteridge, Xiaowen Dong, Michael Bronstein, Francesco Di Giovanni

Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions.

Ranked #3 on Graph Classification on Peptides-func

no code implementations • 28 Nov 2022 • Yin-Cong Zhi, Felix L. Opolka, Yin Cheng Ng, Pietro Liò, Xiaowen Dong

To address this, we present a novel, generalized kernel for graphs with node feature data for semi-supervised learning.

no code implementations • 3 Nov 2022 • Bohan Tang, Siheng Chen, Xiaowen Dong

Hypergraph structure learning, which aims to learn the hypergraph structures from the observed signals to capture the intrinsic high-order relationships among the entities, becomes crucial when a hypergraph topology is not readily available in the datasets.

no code implementations • 31 Oct 2022 • Enpei Zhang, Shuo Tang, Xiaowen Dong, Siheng Chen, Yanfeng Wang

To fill this gap, we propose a distributed multi-agent learning model inspired by human collaboration, in which the agents can autonomously detect suitable collaborators and refer to collaborators' model for better performance.

no code implementations • 16 Jun 2022 • Emanuele Rossi, Federico Monti, Yan Leng, Michael M. Bronstein, Xiaowen Dong

We adopt a transformer-like architecture which correctly accounts for the symmetries of the problem and learns a mapping from the equilibrium actions to the network structure of the game without explicit knowledge of the utility function.

1 code implementation • 29 Mar 2022 • Deborah Sulem, Henry Kenlay, Mihai Cucuringu, Xiaowen Dong

The main novelty of our method is to use a siamese graph neural network architecture for learning a data-driven graph similarity function, which allows to effectively compare the current graph and its recent history.

1 code implementation • 12 Jan 2022 • Lucas G. S. Jeub, Giovanni Colavizza, Xiaowen Dong, Marya Bazzi, Mihai Cucuringu

Our local2global approach proceeds by first dividing the input graph into overlapping subgraphs (or "patches") and training local representations for each patch independently.

1 code implementation • NeurIPS 2021 • Xingchen Wan, Henry Kenlay, Robin Ru, Arno Blaas, Michael Osborne, Xiaowen Dong

While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an important problem with numerous real-life applications such as biochemistry and social network analysis.

3 code implementations • ICLR 2022 • Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, Michael M. Bronstein

Most graph neural networks (GNNs) use the message passing paradigm, in which node features are propagated on the input graph.

Ranked #41 on Node Classification on Citeseer

1 code implementation • 23 Nov 2021 • Emanuele Rossi, Henry Kenlay, Maria I. Gorinova, Benjamin Paul Chamberlain, Xiaowen Dong, Michael Bronstein

While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph.

1 code implementation • 4 Nov 2021 • Xingchen Wan, Henry Kenlay, Binxin Ru, Arno Blaas, Michael A. Osborne, Xiaowen Dong

While the majority of the literature focuses on such vulnerability in node-level classification tasks, little effort has been dedicated to analysing adversarial attacks on graph-level classification, an important problem with numerous real-life applications such as biochemistry and social network analysis.

no code implementations • 25 Oct 2021 • Felix L. Opolka, Yin-Cong Zhi, Pietro Liò, Xiaowen Dong

Graph-based models require aggregating information in the graph from neighbourhoods of different sizes.

1 code implementation • NeurIPS 2021 • Xingyue Pu, Tianyue Cao, Xiaoyun Zhang, Xiaowen Dong, Siheng Chen

The model is trained in an end-to-end fashion with pairs of node data and graph samples.

1 code implementation • NeurIPS 2021 • Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard, Francesco Di Giovanni, Xiaowen Dong, Michael M Bronstein

We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE.

no code implementations • 29 Sep 2021 • Emanuele Rossi, Federico Monti, Yan Leng, Michael M. Bronstein, Xiaowen Dong

Strategic interactions between a group of individuals or organisations can be modelled as games played on networks, where a player's payoff depends not only on their actions but also on those of their neighbors.

2 code implementations • 26 Jul 2021 • Lucas G. S. Jeub, Giovanni Colavizza, Xiaowen Dong, Marya Bazzi, Mihai Cucuringu

Our local2global approach proceeds by first dividing the input graph into overlapping subgraphs (or "patches") and training local representations for each patch independently.

no code implementations • ICML Workshop AML 2021 • Xingchen Wan, Henry Kenlay, Binxin Ru, Arno Blaas, Michael Osborne, Xiaowen Dong

Graph neural networks have been shown to be vulnerable to adversarial attacks.

1 code implementation • Findings (NAACL) 2022 • Valentin Hofmann, Xiaowen Dong, Janet B. Pierrehumbert, Hinrich Schütze

The increasing polarization of online political discourse calls for computational tools that automatically detect and monitor ideological divides in social media.

no code implementations • 18 Feb 2021 • Henry Kenlay, Dorina Thanou, Xiaowen Dong

In this paper, we study filter stability and provide a novel and interpretable upper bound on the change of filter output, where the bound is expressed in terms of the endpoint degrees of the deleted and newly added edges, as well as the spatial proximity of those edges.

no code implementations • ICLR Workshop GTRL 2021 • Henry Kenlay, Dorina Thanou, Xiaowen Dong

Graph neural networks are experiencing a surge of popularity within the machine learning community due to their ability to adapt to non-Euclidean domains and instil inductive biases.

1 code implementation • 20 Sep 2020 • Yan Leng, Rodrigo Ruiz, Xiaowen Dong, Alex Pentland

Recommender systems (RS) are ubiquitous in the digital space.

Ranked #1 on Recommendation Systems on YahooMusic Monti (using extra training data)

no code implementations • 23 Aug 2020 • Xingyue Pu, Siu Lun Chau, Xiaowen Dong, Dino Sejdinovic

In this paper, we propose a novel graph learning framework that incorporates the node-side and observation-side information, and in particular the covariates that help to explain the dependency structures in graph signals.

no code implementations • 31 Jul 2020 • Xiaowen Dong, Dorina Thanou, Laura Toni, Michael Bronstein, Pascal Frossard

The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning.

1 code implementation • ICLR 2021 • Binxin Ru, Xingchen Wan, Xiaowen Dong, Michael Osborne

Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimensional and graph-like search spaces amenable to BO.

no code implementations • 12 Jun 2020 • Yin-Cong Zhi, Yin Cheng Ng, Xiaowen Dong

We propose a graph spectrum-based Gaussian process for prediction of signals defined on nodes of the graph.

no code implementations • 19 Dec 2019 • Diego Granziol, Robin Ru, Stefan Zohren, Xiaowen Dong, Michael Osborne, Stephen Roberts

Graph spectral techniques for measuring graph similarity, or for learning the cluster number, require kernel smoothing.

no code implementations • 12 Jul 2019 • Kaige Yang, Xiaowen Dong, Laura Toni

In terms of network regret (sum of cumulative regret over $n$ users), the proposed algorithm leads to a scaling as $\tilde{\mathcal{O}}(\Psi d\sqrt{nT})$, which is a significant improvement over $\tilde{\mathcal{O}}(nd\sqrt{T})$ in the state-of-the-art algorithm \algo{Gob. Lin} \Ccite{cesa2013gang}.

no code implementations • 11 Feb 2019 • Kaige Yang, Xiaowen Dong, Laura Toni

We provide a theoretical analysis of the representation learning problem aimed at learning the latent variables (design matrix) $\Theta$ of observations $Y$ with the knowledge of the coefficient matrix $X$.

no code implementations • ICML 2020 • Yan Leng, Xiaowen Dong, Junfeng Wu, Alex Pentland

Individuals, or organizations, cooperate with or compete against one another in a wide range of practical situations.

no code implementations • 3 Jun 2018 • Xiaowen Dong, Dorina Thanou, Michael Rabbat, Pascal Frossard

The construction of a meaningful graph topology plays a crucial role in the effective representation, processing, analysis and visualization of structured data.

no code implementations • 18 Apr 2018 • Diego Granziol, Binxin Ru, Stefan Zohren, Xiaowen Dong, Michael Osborne, Stephen Roberts

Graph spectra have been successfully used to classify network types, compute the similarity between graphs, and determine the number of communities in a network.

no code implementations • 4 Nov 2016 • Dorina Thanou, Xiaowen Dong, Daniel Kressner, Pascal Frossard

Effective information analysis generally boils down to properly identifying the structure or geometry of the data, which is often represented by a graph.

no code implementations • 12 Jul 2016 • Renata Khasanova, Xiaowen Dong, Pascal Frossard

The analysis of large collections of image data is still a challenging problem due to the difficulty of capturing the true concepts in visual data.

2 code implementations • 30 Jun 2014 • Xiaowen Dong, Dorina Thanou, Pascal Frossard, Pierre Vandergheynst

We show that the Gaussian prior leads to an efficient representation that favors the smoothness property of the graph signals.

no code implementations • 25 Apr 2014 • Xiaowen Dong, Dimitrios Mavroeidis, Francesco Calabrese, Pascal Frossard

In this paper, we propose a novel approach towards multiscale event detection using social media data, which takes into account different temporal and spatial scales of events in the data.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.